将此存储库克隆到Your ComfyUI root directoryComfyUIcustom_nodes
并安装依赖的 Python 包:
cd Your_ComfyUI_root_directoryComfyUIcustom_nodes git 克隆 https://github.com/Bin-sam/DynamicPose-ComfyUI.git pip install -r 要求.txt
下载预训练模型:
./pretrained_weights/
|-- denoising_unet.pth
|-- motion_module.pth
|-- pose_guider.pth
|-- reference_unet.pth
|-- rtmpose
| |-- rtmw-x_simcc-cocktail14_pt-ucoco_270e-384x288-f840f204_20231122.pth
| |-- rtmw-x_8xb320-270e_cocktail14-384x288.py
| |-- rtmdet_m_640-8xb32_coco-person.py
| |-- rtmdet_m_8xb32-100e_coco-obj365-person-235e8209.pth
| |-- rtmpose-x_8xb256-700e_coco-384x288.py
| |-- rtmpose-x_simcc-body7_pt-body7_700e-384x288-71d7b7e9_20230629.pth
|-- DWPose
| |-- dw-ll_ucoco_384.onnx
| |-- yolox_l.onnx
下载剪辑图像编码器(例如 sd-image-variations-diffusers )并将其放在Your_ComfyUI_root_directoryComfyUImodelsclip_vision
下
下载vae(例如sd-vae-ft-mse)并将其放在Your_ComfyUI_root_directoryComfyUImodelsvae
下
下载stable-diffusion-v1-5(例如stable-diffusion-v1-5)并将其放在Your_ComfyUI_root_directoryComfyUImodelsdiffusers
下
稳定扩散-v1-5_unet
Moore-AnimateAnyone 预训练模型
DWpose 模型下载链接位于标题“DWpose for ControlNet”下。
上述模型需要放在 pretrained_weights 文件夹下,如下所示:
使用管道示例
这个工作流程是 Pose_to_video